CS 6281: Topics in Computer Science II: User Generated Content Analyses using Automated Discourse Processing (Semester I, AY2015/2016)

CS 6281: Topics in Computer Science II User Generated Content Analyses using Automated Discourse Processing (AY2015/2016: Semester I)
Professor	Dr. Diane Litman (Litman [@ comp.nus.edu.sg])
When & Where	Thu 1600-1800: new room is TR5 (COM1-0218) (original room was SR@LT19)
Office Hours	After class, or by appointment in COM1-03-03, 6516 2803
Description	This course will examine the automated analyses of textual user generated content -- e.g., social media, student essays and scientific documents -- using state-of-the-art natural language processing tools and frameworks for discourse understanding. In particular, we will focus on applications and analyses that emphasize the effects of dialogue and discourse processing: inclusive of argument mining, helpfulness prediction, automated summarization, revision analysis, discourse parsing, error correction/detection, corpus creation, social media. We will also investigate educational applications in detail, inclusive of peer review, automatic grading, and learning analytics. Prerequisites: Natural Language Processing OR consent of the instructor
Required Work	Class Project (50%): proposal/progress: 10%, presentation: 5%, report: 25%, STePS: 10% Class Presentations of Readings (30%) Commentaries on other Readings (20%) We will also be participating in the SoC projects program

Week/Lead	Materials	Topic and Readings (open to discussion!)
Week 1 Litman	NB (CHI 2012) Homework Slides (posted on IVLE)	Computational Discourse Webber, B., Egg, M., & Kordoni, V. (2012). Discourse structure and language technology. Natural Language Engineering, 18(4), 437-490. Optional: Webber, B., & Joshi, A. (2012). Discourse Structure and Computation: Past, Present and Future. Proceedings of the ACL Special Workshop on Rediscovering 50 Years of Discoveries, 42-54. Discourse Processing Tutorial by Manfred Stede (slides)
Week 2 Litman	Commentary Instructions Presentation Instructions Project Discussion	Discourse-Enabled User Generated Content Analysis Last week's readings Baldwin, T. (2014). Semantic Analysis of Social Media. Invited keynote at Third Joint Conference on Lexical and Computational Semantics Eisenstein, J. (2015). Variation and Change in Online Writing. Invited keynote at NAACL SocialNLP workshop. Optional: Baldwin, T. (2014). Text Processing of Social Media, Series of guest lectures as part of Language Technology II (Saarland University) ACL 2015 Workshop on Noisy User-generated Text.
Week 3 Prasad (first 2 papers), Fang (last 2 papers	Beginning this week, class will meet in TR5 (COM1-0218) for the rest of the semester. First commentaries due 48 hours before class! Also, you should be making an appointment with me to discuss your project. Here is a list of some annotated corpora that could be used for your project.	Topic and Entity Structures Purver, M. (2011). Topic segmentation. In: G. Tur and R. de Mori (eds.), Spoken Language Understanding: Systems for Extracting Semantic Information from Speech. Hoboken NJ:Wiley. Chapter 11. Barzilay, R., and Lapata, M. (2005). Modeling local coherence: an entity-based approach. Proceedings of the 43rd Annual Meeting of the ACL, 141-148. Hearst, M. A.(1994). Multi-Paragraph Segmentation of Expository Text. Proceedings of the 32nd Meeting of the Association for Computational Linguistics. Riedl, M., and Biemann, C. (2012). How text segmentation algorithms gain from topic models. Proceedings Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 553-557. Software TextTiling Brown Coherence Toolkit
Week 4 Phandi, Chandrasekaran	Project discussions deadline.	Functional Structures Teufel, S., & Kan, M. Y. (2011). Robust argumentative zoning for sensemaking in scholarly documents. Scholarly Documents. Advanced Language Technologies for Digital Libraries 154-170. Burstein, J., Marcu, D. and Knight, K. (2003). Finding the WRITE stuff: Automatic identification of discourse structure in student essays. IEEE Intelligent Systems, 18(1):32–39. Guo, Y. and Reichart, R. and Korhonen, A. (2013). Improved Information Structure Analysis of Scientific Documents Through Discourse and Lexical Constraints. Proceedings of NAACL-HLT, 928-937. Saghdha, D. O., and Teufel, S. (2014). Unsupervised learning of rhetorical structure with un-topic models. Proceedings of COLING, 2-13.
Week 5 Feng, Asharaf	Project proposals due (in IVLE) by 23:59:59 on September 10! Please remember to follow the detailed instructions for writing the proposals.	Predicate-Argument Structures Lin, Ziheng, & Ng, Hwee Tou, & Kan, Min-Yen (2014). A PDTB-Styled End-to-End Discourse Parser. Natural Language Engineering 20:2, 51-184. Ji, Y., & Eisenstein, J. (2015). One Vector is Not Enough: Entity-Augmented Distributed Semantics for Discourse Relations. Transactions Of The Association For Computational Linguistics, 3, 329-344. Software PDTB-Styled End-to-End Discourse Parser Updown CoNLL 2015 Shared Task Shallow Discourse Parsing
Week 6 Asharaf, Kundu		Tree-Like Structures Joty, S., Carenini, G., Ng, R. and Mehdad, Y. (2013). Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 486–496. Ji, Y. and Eisenstein, J. (2014). Representation Learning for Text-level Discourse Parsing, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 13-24. Feng, V. W. and Hirst, G. (2014). A Linear-Time Bottom-Up Discourse Parser with Constraints and Post-Editing, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 511–521. Li, J., Li, R, and Hovy, E. (2014). Recursive Deep Models for Discourse Parsing. Proceedings Empirical Methods in Natural Language Processing, 2061–2069, Optional W. C. Mann and S. A. Thompson. (1988). Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243–281. CODRA: A Novel Discriminative Framework for Rhetorical Analysis, Shafiq Joty, Giuseppe Carenini, Raymond T. Ng Computational Linguistics September 2015, Vol. 41, No. 3: 385 Software Document-level Discourse Parser RST-Style Discourse Parser RSTParser Fast RST Discourse Parser Two Practical RST parsers
Recess Week
Week 7 Chandrasekaran, Feng		Corpora and Annotation Liakata, M., Teufel, S., Siddharthan, A., and Batchelor, C. (2010). Corpora for the Conceptualisation and Zoning of Scientific Papers . Proceedings LREC. Kawahara, D., Machida, Y., Shibata, T., Kurohashi, S., Kobayashi, H., and Sassano, M. (2014). Rapid Development of a Corpus with Discourse Annotations using Two-stage Crowdsourcing. Proceedings Coling. Carlson, L., Marcu, D., and Okurowski, M. E. (2003). Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory. In J. van Kuppevelt and R. Smith (eds.), Current Directions in Discourse and Dialogue. Prasad, R., Webber, B., & Joshi, A. (2014). Reflections on the Penn Discourse TreeBank, Comparable Corpora, and Complementary Annotation. Computational Linguistics, 40(4), 921-950. Corpora Argumentative Zoning Corpus RST Discourse Treebank PDTB
Week 8 Ilievski, Litman	AI2/Kaggle commonsense competition	Integrating/Comparing Structures; Blogs Cardoso, P., M. Taboada and T. Pardo (2013). On the contribution of discourse to topic segmentation. Proceedings of the 14th Annual SIGDial Meeting on Discourse and Dialogue. Feng, V. W., Lin, Z., and Hirst, G. (2014). The Impact of Deep Hierarchical Discourse Structures in the Evaluation of Text Coherence.Proceedings of the 25th International Conference on Computational Linguistics. Shamima Mithun and Keuka Kosseim. (2013). Measuring the Effect of Discourse Relations on Blog Summarization. Proceedings of IJNLP. Matt Gerber, Andrew Gordon and Kenji Sagae. (2010). Open-domain Commonsense Reasoning Using Discourse Relations from a Corpus of Weblog Stories.. Proceedings NAACL HLT Workshop.
Week 9 Yap, Phandi	Project progress report due (in IVLE) by 23:59:59 on October 15! Instructions for writing the progress report.	Educational Applications Beck, C. Streicher, A. and Zielinski, A. (2014). Using Text Segmentation Algorithms for the Automatic Generation of E-Learning Courses. Proceedings 3rd Conference on Lexical and Computational Semantics. Alharbi, G. and Hain, T. (2015). Using Topic Segmentation Models for the Automatic Organisation of MOOCs resources. Proceedings Educational data Mining. Somasundaran, S., Burstein, J. and Chodorow, M. (2014). Lexical Chaining for Measuring Discourse Coherence Quality in Test-taker Essays. Proceedings of COLING. Rahimi, Z., Litman, D., Wang, E. and Correnti, R. (2015). Incorporating Coherence of Topics as a Criterion in Automatic Response-to-Text Assessment of the Organization of Writing, Proceedings 10th NAACL Workshop on Innovative Use of NLP for Building Educational Applications, 20-30.
Week 10 Ilievski, Litman	Templates you *must* use for submitting your project paper. Paper can be no longer than 4 pages before references (i.e., short paper constraints apply). More details on supplemenary materials that you may submit, as well as tips for writing a short paper, can be found here.	Argument Mining Nitin Madnani, Michael Heilman, Joel Tetreault, and Martin Chodorow. (2012). Identifying high-level organizational elements in argumentative discourse. Proceedings of NAACL. Elena Cabrio, Sara Tonelli, and Serena Villata. (2013). From Discourse Analysis to Argumentation Schemes and Back: Relations and Differences. In Joao Leite, Tran Cao Son, Paolo Torroni, Leon Torre, and Stefan Woltran, editors, Proceedings of 14th International Workshop on Computational Logic in Multi-Agent Systems. Stab, C., and Gurevych, I. (2014). Identifying Argumentative Discourse Structures in Persuasive Essays. Proceedings EMNLP. Peldszus, A. (2014). Towards segment-based recognition of argumentation structure in short texts. Proceedings First Workshop on Argumentation Mining (ACL). Optional (hot off the presses!) Andreas Peldszus and Manfred Stede. (2015) Joint prediction in MST-style discourse parsing for argumentation mining. Proceedings EMNLP., Andreas Peldszus, Manfred Stede. (preprint) An annotated corpus of argumentative microtexts. Corpora Argumentative Microtexts Argument-annotated essays and other stuff More to come
Week 11 Prasad, Kundu		Review Analysis Gerani, S., Mehdad, Y., Carenini, G., Ng. R., and Nejat, B. (2014). Abstractive Summarization of Product Reviews Using Discourse Structure. Proceedings EMNLP. 1602-1613. Zhang, Q., Qian, J., Chen, H., Kang, J. and Huang, X. (2013). Discourse Level Explanatory Relation Extraction from Product Reviews Using First-Order Logic. Proceedings EMNLP. Trivedi, R., and Eisenstein, J. (2013). Discourse Connectors for Latent Subjectivity in Sentiment Analysis. Proceedings of NAACL-HLT, 808-813. Yang, B. and Cardie, C. (2014). Context-Aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization. Proceedings ACL. Corpora RST: Discourse Relations Reference Corpus
Week 12 Yap, Fang	First draft of project paper due (in IVLE) by 23:59:59 on Nov. 5!!	Twitter, Slashdot, Yahoo! Answers Mukherjeet, S. and Bhattacharya, P. (2012). Sentiment Analysis in Twitter with Lightweight Discourse Analysis. Proceedings of Coling. Allen, K., Carenini, G. and Ng. R (2014). Detecting Disagreement in Conversations using Pseudo-Monologic Rhetorical Structure. Proceedings EMNLP. Jansen, P, Surdeanu, M. and Clark, P. (2014). Discourse Complements Lexical Semantics for Non-factoid Answer Reranking. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. R. Sharp, P. Jansen, M. Surdeanu, and P. Clark. (2015). Spinning straw into gold: Using free text to train monolingual alignment models for non-factoid question answering. Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies.
Week 13 Everyone	Final version of project paper due (in IVLE) by 23:59:59 on Nov. 13 (one day more than usual, to address any feedback from presentation).	Project Presentations Each presentation should be done with slides (like a conference) and should be 15 minutes long, with 5 minutes for questions. I will time you and stop you after 15 minutes, so practice!
November 18 (5:30-10) Everyone		STePS (SoC Term Project Showcase)